J Am Pharm Assoc (2003). 2021 Jul-Aug;61(4):484-491.e1. doi: 10.1016/j.japh.2021.02.006. Epub 2021 Feb 19.
Pharmacy staff are responsible for editing poor-quality and difficult-to-read electronic prescription (e-prescription) directions. Machine translation (MT) models are capable of translating free text from 1 sequence into another. However, the quality of MTs of e-prescriptions into pharmacy label directions is unknown.
To determine the types and frequencies of e-prescription direction component errors made by an MT model, pharmacy staff, and prescribers.
A prospective evaluation was conducted on a random sample of 300 patient directions in a test set of e-prescriptions from a mail-order pharmacy. Each row included directions produced by (1) prescribers on e-prescriptions, (2) pharmacy staff on prescription labels, and (3) an open neural MT model. Annotators labeled direction sets for missing direction components, use of abbreviations and medical jargon, and incorrect information (e.g., changing the number of tablets to be taken). The longest common subsequence (LCS) compared the amount of pharmacy staff editing with and without MT.
Out of 279 direction sets labeled, the MT model directions contained no quality issues in 196 (70.3%) samples compared with 187 (67.0%) and 83 (29.8%) samples for pharmacy staff directions and prescriber directions, respectively. The MT model directions contained more incorrect components (n = 23). Median LCS was greater without MT (30.0 vs. 18.5, P < 0.01, Wilcoxon signed-rank test), indicating more editing was needed.
MT could be used to improve the quality of e-prescription directions; however, MT makes high-risk mistakes such as incorrectly predicting the tapering regimen for prednisone. The use of semiautomated MT, where pharmacy staff can review model predictions to detect and resolve quality issues, should be considered to improve safety and decrease total work time compared with current practice. MT has strengths and weaknesses for improving the editing process of the patient directions compared with pharmacy staff alone.
药剂师负责编辑质量差且难以阅读的电子处方（e-prescription）医嘱。机器翻译（MT）模型能够将 1 个序列中的自由文本翻译成另一个序列。然而，将电子处方翻译成药剂科标签医嘱的 MT 质量尚不清楚。
确定 MT 模型、药剂师和开方者在电子处方医嘱成分错误的类型和频率。
对邮购药房的 e-prescription 测试集中的 300 个患者医嘱进行了前瞻性评估。每行包含（1）开方者在 e-prescriptions 中的医嘱、（2）药剂师在处方标签上的医嘱、（3）开放神经 MT 模型生成的医嘱。注释者对缺少医嘱成分、缩写和医学术语、以及不正确信息（例如，改变服用的片剂数量）的医嘱集进行了标记。最长公共子序列（LCS）比较了有 MT 和没有 MT 时的药剂师编辑量。
在 279 个标记的医嘱集中，MT 模型医嘱中没有质量问题的样本有 196 个（70.3%），而药剂师医嘱和开方者医嘱中分别有 187 个（67.0%）和 83 个（29.8%）样本存在质量问题。MT 模型医嘱中包含更多错误成分（n=23）。没有 MT 时的中位数 LCS 更大（30.0 比 18.5，P < 0.01，Wilcoxon 符号秩检验），这表明需要更多的编辑。
MT 可用于提高电子处方医嘱的质量；然而，MT 会犯错误，例如错误地预测泼尼松的逐渐减量方案。应考虑使用半自动 MT，药剂师可以审查模型预测结果以发现并解决质量问题，与当前实践相比，这可以提高安全性并减少总工作时间。与药剂师单独编辑相比，MT 在改善患者医嘱编辑过程方面具有优势和劣势。
